Datasets › VALSE

VALSE (VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena)

Introduced by Letitia Parcalabescu et al. in VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena14 Dec 2021 archive 2025-07-28

We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena. VALSE offers a suite of six tests covering various linguistic constructs. Solving these requires models to ground linguistic phenomena in the visual modality, allowing more fine-grained evaluations than hitherto possible. We expect VALSE to serve as an important benchmark to measure future progress of pretrained V&L models from a linguistic perspective, complementing the canonical task-centred V&L evaluations.

Benchmarks archive 2025-07-28

All 12 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
image-sentence alignment VALSE ViLBERT 12-in-1 average pairwise accuracy 75.1 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE actant swap GPT2 pairwise accuracy 76.9 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE action replacement CLIP pairwise accuracy 75.6 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE coreference standard ViLBERT 12-in-1 pairwise accuracy 75.7 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE coreference clean ViLBERT 12-in-1 pairwise accuracy 69.2 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE counting balanced ViLBERT 12-in-1 pairwise accuracy 76.7 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE counting small numbers ViLBERT 12-in-1 pairwise accuracy 80.2 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE counting adversarial ViLBERT 12-in-1 pairwise accuracy 77.3 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE existence ViLBERT 12-in-1 pairwise accuracy 95.6 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE foil-it (noun phrases) CLIP pairwise accuracy 88.8 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE plurality ViLBERT 12-in-1 pairwise accuracy 72.4 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare
image-sentence alignment VALSE spatial relations GPT1 pairwise accuracy 77.2 VALSE: A Task-Independent Benchmark for Vision and... heidelberg-nlp/valse 7 Compare

Papers archive 2025-07-28

papers with a benchmark row: 1 · with a code link: 1 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (1 of 1 with a benchmark row: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: paper 1 of 1 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 26. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • VALSE foil-it (noun phrases)
  • VALSE coreference clean
  • VALSE coreference standard
  • VALSE actant swap
  • VALSE action replacement
  • VALSE spatial relations
  • VALSE counting adversarial
  • VALSE counting small numbers
  • VALSE counting balanced
  • VALSE plurality
  • VALSE existence
  • VALSE

12 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections